Show simple item record

dc.contributor.authorVarna, Dainius
dc.contributor.authorAbromavičius, Vytautas
dc.date.accessioned2023-09-18T16:19:46Z
dc.date.available2023-09-18T16:19:46Z
dc.date.issued2022
dc.identifier.issn2076-3417
dc.identifier.other(crossref_id)137656373
dc.identifier.urihttps://etalpykla.vilniustech.lt/handle/123456789/113236
dc.description.abstractThe presented research addresses the real-time object detection problem with small and moving objects, specifically the surface-mount component on a conveyor. Detecting and counting small moving objects on the assembly line is a challenge. In order to meet the requirements of real-time applications, state-of-the-art electronic component detection and classification algorithms are implemented into powerful hardware systems. This work proposes a low-cost system with an embedded microcomputer to detect surface-mount components on a conveyor belt in real time. The system detects moving, packed, and unpacked surface-mount components. The system’s performance was experimentally investigated by implementing several object-detection algorithms. The system’s performance with different algorithm implementations was compared using mean average precision and inference time. The results of four different surface-mount components showed average precision scores of 97.3% and 97.7% for capacitor and resistor detection. The findings suggest that the system with the implemented YOLOv4-tiny algorithm on the Jetson Nano 4 GB microcomputer achieves a mean average precision score of 88.03% with an inference time of 56.4 ms and 87.98% mean average precision with 11.2 ms inference time on the Tesla P100 16 GB platform.eng
dc.formatPDF
dc.format.extentp. 1-17
dc.format.mediumtekstas / txt
dc.language.isoeng
dc.relation.isreferencedbyScience Citation Index Expanded (Web of Science)
dc.relation.isreferencedbyScopus
dc.relation.isreferencedbyDOAJ
dc.relation.isreferencedbyINSPEC
dc.relation.isreferencedbyJ-Gate
dc.source.urihttps://www.mdpi.com/2076-3417/12/11/5608
dc.titleA system for a real-time electronic component detection and classification on a conveyor belt
dc.typeStraipsnis Web of Science DB / Article in Web of Science DB
dcterms.accessRightsThis article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/)
dcterms.licenseCreative Commons – Attribution – 4.0 International
dcterms.references77
dc.type.pubtypeS1 - Straipsnis Web of Science DB / Web of Science DB article
dc.contributor.institutionVilniaus Gedimino technikos universitetas
dc.contributor.facultyElektronikos fakultetas / Faculty of Electronics
dc.subject.researchfieldT 001 - Elektros ir elektronikos inžinerija / Electrical and electronic engineering
dc.subject.researchfieldT 007 - Informatikos inžinerija / Informatics engineering
dc.subject.studydirectionE09 - Elektronikos inžinerija / Electronic engineering
dc.subject.vgtuprioritizedfieldsIK0303 - Dirbtinio intelekto ir sprendimų priėmimo sistemos / Artificial intelligence and decision support systems
dc.subject.ltspecializationsL106 - Transportas, logistika ir informacinės ir ryšių technologijos (IRT) / Transport, logistic and information and communication technologies
dc.subject.enconvolutional neural networks
dc.subject.endeep learning
dc.subject.enmachine learning
dc.subject.enobject detection
dc.subject.enSMD component
dcterms.sourcetitleApplied sciences: Special issue: Innovations in intelligent machinery and industry 4.0
dc.description.issueiss. 12
dc.description.volumevol. 11
dc.publisher.nameMDPI
dc.publisher.cityBasel
dc.identifier.doi137656373
dc.identifier.doi10.3390/app12115608
dc.identifier.elaba132099250


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record